Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/arctan303/creator.skill/dev-buildernpx skills add arctan303/creator.skill --skill dev-buildergit clone --depth 1 https://github.com/arctan303/creator.skillWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00071 | $0.00774 |
| Opus 5 | $0.00036 | $0.00387 |
| Sonnet 5 | $0.00014 | $0.00155 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
dev-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
开发技能 (dev-builder)
Purpose
在明确交付契约内实施最小完整变更，并用可复现证据证明行为、范围和风险门禁得到满足。
Trigger
- 0→1 产品已有 Product Spec 和完整 DEV-PLAN。
- 产品变更已有变更记录和增量 Phase。
- 非诊断型维护任务已有预期行为、范围、非目标、完成证据和风险级别。
未知根因的缺陷优先交给 bug-fixer。
Required context
- 当前路线、目标、范围、非目标和 R0/R1/R2 依据。
- 产品路线的 Product Spec、DEV-PLAN 与当前 Phase，或维护路线的任务契约。
- 仓库约束、现有测试、验证入口和用户授权边界。
- 设计规范或视觉产物（如果相关）。
Workflow
- 将任务映射到需求/验收/变更 ID 或维护预期行为。
- 检查仓库与现有修改，保护用户未授权覆盖的工作。
- 按契约实施最小完整修改，持续记录偏离和新风险。
- 执行与风险相称的结构检查、针对性测试、构建或冒烟验证。
- 维护执行且 R0/R1 的轻量小改由当前会话直接完成，不派遣子代理，记入
docs/maintenance/batch.md待复查；不自动触发审查，收尾时提醒“待复查 N 项，是否现在批量审查？”。 - R2 或产品 Phase 只为当前“契约 + diff + 证据”创建一次 fresh reviewer；批量修复结论后，新 diff 最多进行一次聚焦复审。批量复查按“批 ID + 累积 diff + 证据”作为一次审查输入，仅在用户明确同意后启动。
- 若模型容量、网络、工具或宿主中断，保存恢复检查点，恢复后只继续未完成步骤。
Output
- 路线、风险及依据。
- 契约映射、修改文件和实现摘要。
- 验证命令、结果、失败项和跳过项。
- 轻量小改的批处理队列条目（
docs/maintenance/batch.md）与收尾提醒。 - reviewer 结论（如适用）、偏离、阻塞和残余风险。
- 中断时的恢复检查点，而不是虚假的完成结论。
Stop or escalate
- 缺少可判断的目标契约：停止并返回前序阶段。
- 维护任务需要重新定义正确行为或改变公开边界：升级为产品变更。
- 验证失败、证据不足或影响范围无法证明：不得声明完成。
- 同一阻塞问题连续两轮复审仍存在：停止继续生成 reviewer，报告阻塞与所需决策。
- 真实发布、推送、部署或其他外部状态变更没有明确授权：停止在本地验证边界。
References
执行前读取 stage-contract.md。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 57 lines · 71 tokens per session scan A b5877b877b08
dev-builder is a skill published in the GitHub repository arctan303/creator.skill (20 stars, last pushed 27d ago), licensed MIT. It adds 71 tokens to every session and 774 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sentry-fix-issues
Find and fix issues from Sentry using MCP. Use when asked to fix Sentry errors, debug production issues, investigate exceptions, or resolve bugs reported in Sentry. Methodically analyzes stack traces, breadcrumbs, traces, and context to identify root causes.
agent-sop-author
Create (or update) and validate Agent SOPs (Standard Operating Procedures) - markdown-based workflows that guide AI agents through complex, multi-step tasks with RFC 2119 constraints.
skill-creator
Create or improve Zhin Agent skills (SKILL.md). Use when asked to add a skill, write SKILL.md, document a repeatable agent workflow, or refine skill frontmatter/keywords. Triggers: 创建技能, 写 SKILL, skill-creator, 加 skill.
agent-team
Build low-context multi-agent teams with durable handoff, independent review, and user gates. Use when a project needs separate management, execution, and review roles.
agent-team
Build low-context multi-agent teams with durable handoff, independent review, and user gates. Use when a project needs separate management, execution, and review roles.
icode
端到端编码工作流（步骤 06，含可选需求初稿步骤与日志根因分析入口），支持分步手动调用：/icode help (帮助), /icode install (MCP 环境检查+一键安装), /icode init [ ] (需求初稿), /icode log [零散信息...] (日志根因分析→转修复需求), /icode start (全流程), /icode fast (精简全流程), /icode plan (计划), /icode review [N] (审查), /icode merge (定稿), /icode code (编码), /icode deepcheck (复检), /icode audit (终审)…